# How to connect New Relic to OpenAI Dots

> Set up New Relic for OpenAI Dots with Agent200, then check which tools are available to your agent.

- Page: https://www.agent200.com/connectors/new-relic/framework/openai-dots/
- Connector: [New Relic](https://www.agent200.com/connectors/new-relic.md)
- Framework: OpenAI Dots
- Updated: 2026-11-18

## Instructions for AI agents

Goal: connect New Relic to OpenAI Dots with Agent200.
Guide: https://www.agent200.com/connectors/new-relic/framework/openai-dots/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure New Relic is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's New Relic account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on New Relic.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "new_relic" in the tools. The model decides when a New Relic tool is needed; Agent200 executes the call.
7. Check it works with this request: "Ask OpenAI Dots to list the Agent200 tools available for New Relic, including which are read-only."
   What should come back:
   - A list of the New Relic tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in New Relic, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## Overview

This guide connects New Relic to OpenAI Dots through Agent200. When you finish, OpenAI Dots can call the New Relic tools for each of your users.

Every call runs with that user's own New Relic connection: Agent200 runs the OAuth flow, stores and refreshes the tokens, and executes the call. You do not build or maintain a New Relic integration.

- **Connector:** [New Relic](https://www.agent200.com/connectors/new-relic/)
- **Works with:** OpenAI Dots · Your own agent code
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [6 tools](https://www.agent200.com/connectors/new-relic/framework/openai-dots/#tools)
- **Model in examples:** `openai/gpt-5.6-sol`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **New Relic enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **An end user with a New Relic account.** They approve access once, on New Relic's own page.
- **A model for your agent.** The examples use openai/gpt-5.6-sol, through the same Agent200 API key.

## Connect New Relic to OpenAI Dots

### Step 1: Create your Agent200 API key

Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers New Relic and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.

Create an API key: https://agent200.com/platform/apikeys/

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Set up the Agent200 SDK

Add the SDK to your project and create a client with the key from the environment.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Let your user connect New Relic

Each end user authorizes their own New Relic account once, through managed OAuth. If the user has not connected yet, Agent200 returns an authorization link: show it to them, and they approve access on New Relic's own page. Agent200 handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own New Relic account, once.
const connection = await agent200
  .user("user_123")
  .connect("new_relic");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 4: Run with the New Relic tools

Name the user, the model and New Relic in the tools. The model decides when a New Relic tool is needed, and Agent200 executes the call with the user's own connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "What was the error rate of the checkout service in the last hour",
    tools: ["new_relic"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Ask OpenAI Dots to list the Agent200 tools available for New Relic, including which are read-only."

What should come back:

- A list of the New Relic tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.

If no tools appear, check your Agent200 project access for New Relic and make sure its tools are enabled. Tool availability depends on your project setup.

## New Relic tools OpenAI Dots can call

- **Run a NRQL query** (`new_relic_run_nrql_query`, read): Run a NRQL query on the account's metrics, events and logs.
- **Search entities** (`new_relic_search_entities`, read): Find services, hosts and other entities by name or type.
- **Get an entity** (`new_relic_get_entity`, read): Get an entity's details and health status.
- **List alert policies** (`new_relic_list_alert_policies`, read): List the account's alert policies.
- **List alert conditions** (`new_relic_list_alert_conditions`, read): List the conditions in an alert policy.
- **Record a deployment** (`new_relic_create_deployment`, write): Add a deployment marker to an entity.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input, the end user's id and the New Relic tools.
2. **The model picks a tool.** The model decides whether a New Relic tool is needed, and with which arguments.
3. **Agent200 runs the call.** It uses that user's own New Relic connection, within the endpoints and scopes your project allows, and returns the result to the model.
4. **Your app gets the result.** Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

**Each user's own connection.** Connections belong to individual end users. A request for one user never reaches another user's New Relic account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and New Relic enforces what its API grants.

## Troubleshooting

### Why not connect Agent200 to a dot directly?

A dot uses the plugins connected to your ChatGPT account, and ChatGPT’s custom MCP servers cannot send an API key. Building the agent with the Agent200 SDK, as on this page, is the route that works.

### The request says New Relic authorization is required

The end user has not connected New Relic yet, or the connection needs to be approved again. Agent200 returns an authorization link: show it to the user, let them approve access on New Relic's own page, then run the request again.

### OpenAI Dots does not use the New Relic tools

Check that New Relic is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming New Relic in the request, or in the instructions, also helps the model choose the right tool.

### A tool call is refused or returns less than expected

Agent200 runs only what your project allows (services, endpoints and scopes), and New Relic returns only what the end user authorized. Widen the endpoints or scopes in the dashboard if the agent needs more, then ask the user to connect New Relic again so they can approve the new access.

### The results come from the wrong account

Every request names an end user (`user_123` in the examples). Pass the id of the person your agent is working for: Agent200 then uses only that user's New Relic connection, never another user's.

### The API key was pasted into a chat or committed

Create a new key on the [API keys page](https://agent200.com/platform/apikeys/), update `AGENT200_API_KEY` wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.

## Use New Relic with another framework

- [New Relic + Claude](https://www.agent200.com/connectors/new-relic/framework/claude.md)
- [New Relic + ChatGPT](https://www.agent200.com/connectors/new-relic/framework/chatgpt.md)
- [New Relic + Claude Code](https://www.agent200.com/connectors/new-relic/framework/claude-code.md)
- [New Relic + Muse](https://www.agent200.com/connectors/new-relic/framework/muse.md)
- [New Relic + Grok Bot](https://www.agent200.com/connectors/new-relic/framework/grok-bot.md)
- [New Relic + Claude Duet](https://www.agent200.com/connectors/new-relic/framework/claude-duet.md)
- [New Relic + Hermes Agent](https://www.agent200.com/connectors/new-relic/framework/hermes-agent.md)
- [New Relic + OpenClaw](https://www.agent200.com/connectors/new-relic/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
